• Journal of the Korean Society of Groundwater Environment
• /
• 제6권2호
• /
• pp.66-75
• /
• 1999

This work was initiated to investigate current situation and problems in applying groundwater-related models for various kinds of environmental impact assessment in Korea. and therefore. to enhance appropriate application in the future. This study was carried out with 544 and 16 documents of EIA (Environmental Impact Assessment. Law of Environmental Impact Assessment) and Mineral-Water EIA (“the environmental impact investigation for mineral water developments”; Law of Drinking Water Management). respectively. It was revealed that there were considerably many cases which may cause serious impacts on subsurface environments in EIA. However. none applied groundwater models. Generally, the influences on subsurface system were underestimated or even ignored in EIA. For Mineral-Water EIA. groundwater models wert applied. in general. But. numerous and serious problems were noted: limited number of calibration parameters and parameter types. setting boundary conditions without adequate bases. recharge rates several times higher than precipitation rates. numerically unstable results. etc. Such kinds of misusages seem to be caused by modelers larking in professional knowledges. To solve the problems revealed from this study. more systematic re-education programs are suggested.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 한국항해항만학회 2022년도 춘계학술대회
• /
• pp.275-276
• /
• 2022

VTS operators instruct ships to wait for entry and departure to sail in one-way to prevent ship collision accidents in ports with narrow routes. Currently, the instructions are not based on scientific and statistical data. As a result, there is a significant deviation depending on the individual capability of the VTS operators. Accordingly, this study built a 1d-convolutional neural network model by collecting ship and weather data to predict the exact travel time for ship entry/departure waiting for instructions in the port. It was confirmed that the proposed model was improved by more than 4.5% compared to other ensemble machine learning models. Through this study, it is possible to predict the time required to enter and depart a vessel in various situations, so it is expected that the VTS operators will help provide accurate information to the vessel and determine the waiting order.

• Proceedings of the Korea Water Resources Association Conference
• /
• 한국수자원학회 2021년도 학술발표회
• /
• pp.481-481
• /
• 2021

서울시는 '10년, '11년, '18년의 기록적인 호우로 인해 막대한 재산피해를 기록하였다. 이로 인해 서울시는 수재해 최소화 대책의 필요성을 인지하여 방재시설물 확충 등의 구조적 대책과 함께 침수지역 예측, 호우 영향 예보와 관련된 비구조적 대책 수립을 위해 노력하고 있다. 그 일환으로 2018~2019년 『서울시 강한 비구름 유입경로 및 침수위험도 예측 용역』 수행을 통해 레이더 실황강우 기반의 강한 비구름 이동경로 추정 기술, 강우시나리오 기반의 침수위험지역추정 기술이 적용된 서울시 도시침수 예측시스템을 개발하였다. 또한, 침수피해에 선제적으로 대응하기 위해 2019~2020년 『서울시 내수침수 위험지역 실시간 예측기술 개발』을 통하여 이류모델 기반의 예측강우정보 추정 기술, 예측강우정보 기반의 실시간 침수위험지역 추정기술을 적용하였다. 현재 서울시 도시침수 예측시스템은 서울시 전역의 강우 및 침수정보를 제공하며, 관로 113,286개(전체 385,768개), 맨홀 106,097개(전체 272,133개), 빗물펌프장 117개소(전체 121개소)가 반영되어 있다. 서울시 도시침수 예측시스템에서는 서울시 25개 자치구를 대상으로 실황 및 예측 강우정보, 강한 비구름에 대한 이동경로정보, 시나리오 및 실시간 침수정보를 제공하고 있다. 강우정보는 10분 및 1시간 단위 AWS 실황정보와 10분 단위 이류모델 기반 예측정보, 1시간 단위 LDAPS 기반 예측정보를 제공한다. 또한, 레이더 실황정보를 통해 판별된 강한 비구름에 대해 10분 단위 1시간 예측경로를 제공한다. 침수정보는 총강우량, 강우지속기간, 빗물받이효율 조건을 반영한 강우시나리오 기반의 6m 고해상도 격자단위 침수시나리오 정보와 자치구별 침수위험정보를 제공한다. 또한, 이류모델 기반의 레이더 예측정보를 이용하여 실시간 침수 예측정보를 제공한다. 향후 서울시 내 모든 수방시설물의 적용, 관로 유출구별 기점수위 반영, 관측자료를 이용한 도시유출 및 도시침수 모델 최적화 등 지속적으로 고도화를 수행하고자 하며, 서울시 도시침수 예측시스템을 통해 서울시 및 자치구 풍수해 담당자가 침수피해를 대비, 대응할 수 있을 것으로 기대된다.

• The Transactions of the Korea Information Processing Society
• /
• 제13권4호
• /
• pp.199-207
• /
• 2024

Local reservoirs are crucial sources for agricultural water supply, necessitating stable water level management to prepare for extreme climate conditions such as droughts. Water level prediction is significantly influenced by local climate characteristics, such as localized rainfall, as well as seasonal factors including cropping times, making it essential to understand the correlation between input and output data as much as selecting an appropriate prediction model. In this study, extensive multivariate data from over 400 reservoirs in Jeollabuk-do from 1991 to 2022 was utilized to train and validate a water level prediction model that comprehensively reflects the complex hydrological and climatological environmental factors of each reservoir, and to analyze the impact of each input feature on the prediction performance of water levels. Instead of focusing on improvements in water level performance through neural network structures, the study adopts a basic Feedforward Neural Network composed of fully connected layers, batch normalization, dropout, and activation functions, focusing on the correlation between multivariate input data and prediction performance. Additionally, most existing studies only present short-term prediction performance on a daily basis, which is not suitable for practical environments that require medium to long-term predictions, such as 10 days or a month. Therefore, this study measured the water level prediction performance up to one month ahead through a recursive method that uses daily prediction values as the next input. The experiment identified performance changes according to the prediction period and analyzed the impact of each input feature on the overall performance based on an Ablation study.

• KIPS Transactions on Software and Data Engineering
• /
• 제8권2호
• /
• pp.67-78
• /
• 2019

Accurate electric load forecasting is very important in the efficient operation of the smart grid. Recently, due to the development of IT technology, many works for constructing accurate forecasting models have been developed based on big data processing using artificial intelligence techniques. These forecasting models usually utilize external factors such as temperature, humidity and historical electric load as independent variables. However, due to diverse internal and external factors, historical electrical load contains many missing data, which makes it very difficult to construct an accurate forecasting model. To solve this problem, in this paper, we propose a random forest-based missing data recovery scheme and construct an electric load forecasting model based on multilayer perceptron using the estimated values of missing data and external factors. We demonstrate the performance of our proposed scheme via various experiments.

• Journal of the Korea Society of Computer and Information
• /
• 제28권2호
• /
• pp.201-207
• /
• 2023

In this paper, we propose an optimal model for mid to long-term price prediction of agricultural products using LGBM, MLP, LSTM, and GRU to compare and analyze the three strategies of the Multi-Step Time Series. The proposed model is designed to find the optimal combination between the models by selecting methods from various angles. Prior agricultural product price prediction studies have mainly adopted traditional econometric models such as ARIMA and LSTM-type models. In contrast, agricultural product price prediction studies related to Multi-Step Time Series were minimal. In this study, the experiment was conducted by dividing it into two periods according to the degree of volatility of agricultural product prices. As a result of the mid-to-long-term price prediction of three strategies, namely direct, hybrid, and multiple outputs, the hybrid approach showed relatively superior performance. This study academically and practically contributes to mid-to-long term daily price prediction by proposing an effective alternative.

• Proceedings of the Korea Water Resources Association Conference
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.255-255
• /
• 2023

우리나라의 경우 집중호우와 돌발홍수로 인한 침수 발생에 대응하기 위해 유역 및 하천관리 사업, 각종 풍수해 예방사업 등을 추진하고 있으며, 관련 분야의 스마트기술 도입을 적극 추진하고 있다. 그러나, 2013년 노량진 상수도관 공사 현장 사고, 2019년 신월 빗물저류 배수시설 현장 사고 등과 같은 건설현장 침수 피해 사고가 지속적으로 발생하고 있다. 또한, 건설현장의 다양한 조건 및 시시각각 변화하는 상황에 따라 구조적 대책 및 대응방안을 수립하는 데 한계가 있으며 지금까지는 법, 제도에 기초한 대응 매뉴얼을 제작·배포하여 현장 근로자 교육을 실시하는 수준에서 진행되어 왔다. 본 연구에서는 건설현장의 자연재해, 특히 수재해에 대응하기 위해 보다 과학적인 방법을 통한 현장 침수 예경보 체계를 수립하였으며, 강우예측-침수예측-침수예경보 생산-현장 상황전파에 이르는 일련의 시스템을 개발하여 공사별, 규모별, 공정별 침수 대응 솔루션을 제공하고자 한다. 건설현장 침수예경보 시스템 개발의 주요 내용은 요소기술 개발이며, 간략하게 정리하면 다음과 같다. ① 강우 예측정보 생산: 현장에서 발생하는 집중호우를 고려하는 실시간 강우측정 자료와 연계한 초단기 강우예측 기술 개발, ② 침수 예측모델 개발: 현장의 시공간적 특성, 수재해 피해의 유형 등을 반영할 수 있는 침수피해 예측 모델 개발, ③ 침수예경보 의사결정 방법론 개발: 침수 피해 예경보를 위한 침수 위험단계 세분화 및 노모그래프 개발과 모델 적용(예측정확도 85% 이상), 이를 통합하여 건설현장 침수예경보 시스템 개발을 수행하게 된다. 연구에서 개발된 침수 예경보 통합 시스템은 향후 수재해로 인한 건설현장의 인명, 재산 피해 최소화에 기여할 것으로 기대된다.

• Journal of Aerospace System Engineering
• /
• 제17권2호
• /
• pp.62-70
• /
• 2023

We proposed a technique for predicting Stress-Life (S-N) curve or fatigue life using geometric features of a ply-overlap joint structure in which plies of two composite materials are partially or wholly laminated and bonded. Geometric features that could affect fatigue properties of a structure were selected as variables. By analyzing relationships between geometric variables and material constants of the Epaarachchi-Clausen model, a fatigue model for composites, relational expressions of these two factors were proposed. To verify the prediction accuracy of the proposed method, fatigue life of a CFRP/GFRP ply-overlap joint was predicted. Predicted life and life obtained by test data-based model were compared to actual life. High prediction accuracy was confirmed by calculating the coefficient of determination of the predicted S-N curve.

• Journal of Internet Computing and Services
• /
• 제24권6호
• /
• pp.49-55
• /
• 2023

In this study, models for predicting the popularity of mukbang content on YouTube were proposed, and factors influencing the popularity of mukbang content were identified through post-analysis. To accomplish this, information on 22,223 pieces of content was collected from top mukbang channels in terms of subscribers using APIs and Pretty Scale. Machine learning algorithms such as Random Forest, XGBoost, and LGBM were used to build models for predicting views and likes. The results of SHAP analysis showed that subscriber count had the most significant impact on view prediction models, while the attractiveness of a creator emerged as the most important variable in the likes prediction model. This confirmed that the precursor factors for content views and likes reactions differ. This study holds academic significance in analyzing a large amount of online content and conducting empirical analysis. It also has practical significance as it informs mukbang creators about viewer content consumption trends and provides guidance for producing high-quality, marketable content.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 한국경영과학회 2008년도 추계학술대회 및 정기총회
• /
• pp.324-328
• /
• 2008

금융산업에서 고객의 이탈비율은 기대수익에 영향을 미친다는 점에서 예측이 필요한 부분이며 최근 들어 정확한 예측을 통한 비용관리가 이루어지면서 고객 이탈을 예측하는 것이 중요한 문제로 떠오르고 있다. 그러나 보험 고객 데이터가 대용량이고 불균형한 출력 값을 갖는 특성으로 인해 기존의 방법으로 예측 모델을 만드는 것이 적합하지 않다. 본 연구에서는 대용량 데이터를 처리하는 데 효과적으로 알려져 있는 Trust-region Newton method를 적용한 로지스틱 회귀분석을 통해 이탈고객을 예측하는 것을 주된 연구로 하며, 불균형한 데이터에서의 예측정확도를 높이기 위해 Oversampling, Clustering, Boosting 등을 이용하여 고객 데이터에 적합한 이탈 고객 예측 모형을 제시하고자 한다.